CN106020715A - Storage pool capacity management - Google Patents

Storage pool capacity management Download PDF

Info

Publication number
CN106020715A
CN106020715A CN201610164308.9A CN201610164308A CN106020715A CN 106020715 A CN106020715 A CN 106020715A CN 201610164308 A CN201610164308 A CN 201610164308A CN 106020715 A CN106020715 A CN 106020715A
Authority
CN
China
Prior art keywords
volume
capacity
subset
module
storage
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201610164308.9A
Other languages
Chinese (zh)
Other versions
CN106020715B (en
Inventor
G·爱勒托里
H·H·路德维格
N·S·曼德格里
宋旸
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
International Business Machines Corp
Original Assignee
International Business Machines Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by International Business Machines Corp filed Critical International Business Machines Corp
Publication of CN106020715A publication Critical patent/CN106020715A/en
Application granted granted Critical
Publication of CN106020715B publication Critical patent/CN106020715B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601—Interfaces specially adapted for storage systems
    • G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
    • G06F3/0608—Saving storage space on storage systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601—Interfaces specially adapted for storage systems
    • G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
    • G06F3/0629—Configuration or reconfiguration of storage systems
    • G06F3/0631—Configuration or reconfiguration of storage systems by allocating resources to storage systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601—Interfaces specially adapted for storage systems
    • G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
    • G06F3/0638—Organizing or formatting or addressing of data
    • G06F3/064—Management of blocks
    • G06F3/0641—De-duplication techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601—Interfaces specially adapted for storage systems
    • G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
    • G06F3/0638—Organizing or formatting or addressing of data
    • G06F3/0644—Management of space entities, e.g. partitions, extents, pools
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601—Interfaces specially adapted for storage systems
    • G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
    • G06F3/067—Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601—Interfaces specially adapted for storage systems
    • G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
    • G06F3/0671—In-line storage system
    • G06F3/0683—Plurality of storage devices
    • G06F3/0685—Hybrid storage combining heterogeneous device types, e.g. hierarchical storage, hybrid arrays

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention discloses storage pool capacity management. Embodiments relate to a pool of persistent storage volumes. Capacity of the volumes is managed to ensure continued operation and function of the volumes with respect to their corresponding storage pool capacity threshold(s). A background process groups the volumes within each pool into one or more clusters based on a similarity or commonality characteristic. The background process selectively performs one or more space savings techniques of a copy of a selected volume, measures impact data associated with the techniques, and maintains the data. At such time as the threshold level is approached for a storage pool, one or more space reduction actions take place on constituent volumes in view of the background process and the associated groups. The reduction action includes implementation of a space saving technique, such as compression and/or thinning, of one or more volumes in one or more clusters in an associated storage pool.

Description

Storage pool capacity management
Technical field
The present invention relates to the management of lasting memory capacity.More particularly, the present invention relate to space Save impact analysis and assessment and one or more places of the execution for space-saving techniques Reason.
Background technology
Compressing and simplifying pre-configured is to be used to reduce memory capacity in data center use (also referred to as storing trace (footprint)) is so that the available technology of more storage. Storage administrator can specify storage volume to be compression, intensive or (thin) that simplify, Each management strategy is used not only in the initial pre-configured time, but also is used in stable state life cycle Period.But, using any one in above technology to reduce memory capacity may be to application Can have negative effect.Such as, the storage volume from compression is read out requiring that this volume stands needs The decompression technique of additional treatments.Meanwhile, it is read out may being also required to add from the volume simplified Process, the such as metadata lookup before data access.Read from the volume rolled up or simplify of compression Fetch data and introduce I/O time delay.
Balance is there is between the performance and the application of data storage technology of data storage technology.Property Energy impact and capacity saving are the functions of live load (workload), and in different works Make to be extensively varied between loadtype.Such as, if roll up the storage resided therein in application Pond exists the free space of abundance, then volume is compressed or simplifies have minimum benefit.Just In this point, storage trace reduces technology (such as compress and simplify pre-configured) for application The memory capacity discharged in storage pool that is close or that exceeded capacity threshold is desirable.
Summary of the invention
The present invention includes for comprising one about the availability management of memory space is one or more Or the method for storage pool, computer program and the system of multiple volume.
In an aspect, it is provided that the capacity of a kind of storage volume managed in storage pool, more The method making volume management and capacity uncoupling (decouple) body.Two are utilized to mainly comprise Aspect, including uncoupling and selection.Uncoupling relates to compression based on one or more volumes or essence The estimation that the capacity of letter is saved.The subset of the volume operated with the first state is selected from each storage pool, And the copy of volume is simplified or compressed.Thereafter, measure and record along with the subset selected Any capacity change.It addition, measure and record from the live load in the subset selected Performance change.Capacity based on record and performance change data select and perform optimal spatial to subtract The subset of little trick.Perform at least one action from this subset when needed, so that the One State Transferring is the second state.
In another aspect, it is provided that the computer program of a kind of capacity managing storage pool. Described computer program includes the computer comprising the program code that the unit that can be processed performs Readable storage device.Described program code solves two key components, including uncoupling and Select.More specifically, program code makes the capacity from the reduction action of one or more spaces save Save estimates the actual execution uncoupling with such action.The journey being associated with the estimation of capacity Sequence code selects the subset (wherein wanting selected volume to operate) of volume with the first state from each pond, And the copy of the subset of each selection is performed the first space reduction action.Thereafter, described generation Code is measured along with the capacity of the subset selected changes, and records this change.Described program code Also measure the performance change of live load from the switching in the subset selected, and record should Performance change.Described code capacity based on record changes and performance change generates for execution The subset of optimal spatial reduction action.Program code is further provided to perform when needed At least one action of the subset of self-generating, wherein this execution makes the first State Transferring be the second shape State.
In another aspect, it is provided that the computer system of a kind of capacity managing storage pool.Institute The system of stating includes processing unit and has the storage pool of two or more storage volume, described place Reason unit is operatively coupled to memorizer, and described storage pool is operatively coupled to processing unit. There is provided with processing unit communication to solve the management instrument of the capacity of storage pool.This instrument includes Coupling module and selection module.The function of this uncoupling module is, estimates from one or many The capacity of individual space reduction action is saved, and makes the actual execution of this estimation and such action Separate.(wherein these volumes are with the first state behaviour from the subset of each pond selection volume for uncoupling module Make), and the copy of the subset of each selection is performed the first space reduction action.Thereafter, This module is measured the capacity being associated with the subset selected and is changed, and records the change of this capacity. It addition, measure and record performance change.Select module capacity based on record and performance change number According to the subset generating optimal spatial reduction action.When needed, module is selected to perform generation At least one action in the subset of optimal spatial reduction action.This execution makes the first State Transferring It it is the second state.
From combining the following detailed description to presently preferred embodiment of accompanying drawing, these features and Advantage and further feature and advantage will be clear from.
Accompanying drawing explanation
Herein with reference to accompanying drawing form the part of this specification.Feature meaning shown in accompanying drawing It is only to illustrate some embodiments of the present invention, and all embodiments of non-invention, unless separately Explicitly indicate.
Fig. 1 describes to illustrate the flow chart of the general introduction that uncoupling processes.
Fig. 2 describes to illustrate the flow chart of the process saved for estimation space.
Fig. 3 describes to illustrate the flow process of the process for predicting storage threshold-violating (violation) Figure.
Fig. 4 describes to illustrate the flow chart of management memory capacity.
Fig. 5 describes to illustrate the block diagram of the assembly of storage pool capacity management system.
Fig. 6 describes the example of cloud computing node.
Fig. 7 describes cloud computing environment.
Fig. 8 describes one group of function modeling layer that cloud computing environment is provided.
Detailed description of the invention
Will readily appreciate that, as in accompanying drawing in this article overall describe and illustrated in the group of the present invention Part can be arranged with diversified different configurations and design.Therefore, below to such as accompanying drawing Middle presented assembly of the invention, the detailed description of embodiment of system and method are not intended to Limit the scope of claimed invention, but be merely representative of the embodiment of the selection of the present invention.
To " embodiment of selection ", " embodiment " or " real in whole this specification Execute example " quote it is meant that the specific feature, structure or the characteristic bag that describe in conjunction with the embodiments Include at least one embodiment of the present invention.Therefore, phrase " embodiment of selection ", " In one embodiment " or " in an embodiment " each place in whole this specification in go out Now it is not necessarily referring to same embodiment.
The embodiment illustrated of the present invention is best understood by with reference to accompanying drawing, in the accompanying drawings, Similar part is all the time by similar numeral appointment.Hereinafter describe and be intended merely to as example, and And be merely exemplary equipment, system and the process consistent with the present invention claimed herein Some embodiment selected.
There are two key components in the management to storage volume, including identifying (identification) and correct (reclamation).Identification relates to estimating and storage trace The space that reduction technology is associated is saved and performance impact.Rectification relates to postponing storage trace and reduces The action of technology, until meeting some standard.Therefore, the two aspect (includes identifying And correct) be uncoupled in the power supply circuit by means of a transformer, until such as storage is saved and has been considered useful or necessity so Time till.
As discussed above, data center is configured with two or more storage pools.One Or multiple application can utilize reside in these ponds one or more in the phase supported of volume The data of association perform application.In order to create memory space in the storage pool being associated, can With to the one or more volume applied compression resided in these ponds and/or simplify pre-configured (this Literary composition is also referred to as simplified) technology.About time requirement and any produced performance cost two Person, to all possible volume applied compression in these ponds or simplify in large scale system may It is unpractiaca.
With reference to Fig. 1, it is provided that illustrate the flow chart (100) of the general introduction that uncoupling processes.Based on The method of sampling of similarity is utilized to alleviate and simplifies with to the application of all possible volume and compress phase The time of association and performance cost.In this regard, come in data center based on similarity Storage volume carry out clustering (cluster) (102).In one embodiment, if volume maps To same application, then they can be considered to be similar, because which increasing they storages The probability of the data of similar type.In one embodiment, if volume show similar with Machine or the reading of order and write I/O ratio or character, then they can be considered to be similar. Such as, two volumes with mainly random writing I/O can be counted as similar.One Pearson came (Pearson) phase in individual embodiment, between the I/O ratio of two or more volumes Close coefficient and can be used as similarity.Therefore, by using correlation, volume can be divided The cluster of composition desired amt.
By to involving in row cluster, as it has been described above, the subset of the volume in each cluster can be selected Select the assessment for compressing and simplify.The space joint that selected volume from each cluster obtains Save and can be used for performance impact value the remaining volume in this cluster is estimated similar characteristic, And in one embodiment, can serve as the guidance for sampling in future.By variable YTotal Distribute to the quantity (104) of the cluster of formed volume, and the cluster counting being associated is become Amount Y carries out initializing (106).For each cluster, minimum of one is utilized to roll up to comment Estimate.By variable XTotalDistribute to clusterYIn be selected for assessment volume subset in number Amount (108), and the volume count variable X being associated is initialized (110).To clusterY In volumeXCopy applied compression or simplify (112), and the work being associated is born Carry copy (114) that is that distribute to compression or that simplify.In order to understand that utilization has been compressed or simplified The implied meaning of process of data, it is thus achieved that save data (116) from compression or the space simplified, And obtain and reduce state from non-space and reduce the state (pair such as compressed or simplify to space Originally) the performance impact data (118) that switching is associated.Will be in step (116) and (118) The data obtained are stored in (120) in the knowledge base being associated.In one embodiment, knowledge Storehouse can local in data center, be not subjected in the volume simplifying or compress, or knowledge base Can be outside data center.In one embodiment, will save what data were associated with space Capacity data is stored in first position, and performance impact data are stored in second position. This primary importance and the second position can be identical position or different positions.Therefore, with pressure Data are saved in the space that contracting or the volume simplified are associated and performance data is acquired.
After step (120), make volume count variable increment (122), then determine poly- Whether apoplexy due to endogenous wind exists other volume (124) any being specified for assessment.As it has been described above, it is each In cluster, a copy of minimum volume is simplified or is compressed, and obtains the performance and sky being associated Between save data to find out the implied meaning that (ascertain) is compressed for this cluster or simplifies. In other words, simplify or the copy that compresses represents cluster.If determined same in step (124) One cluster clusterYMiddle existence is specified for the volume of assessment, then process and return to step (112).But, if determining in step (124) and cluster standing assessment or is designated The most processed for all of volume of assessment, then make cluster counting variable be incremented by (126).As above Described, volume is divided into cluster, and minimum of one clusters.After step (126), determine all Cluster (specifically, in each cluster be specified for assessment all of volume) the most Processed (128).Then return to after negative response to the determination at step (128) place Step (110) processes with any row that involves in specified in clustering the next one.But, to step Suddenly the positive response of the determination at (128) place terminates the process of volume.
The process being estimated storage volume (includes but not limited to live load due to a variety of causes Change, the change etc. of data center) and be periodically repeated.Similarly, a reality Executing in example, shown in Fig. 1 and described process is used as to be repeated based on the cycle So that the data in knowledge base are current background process.In one embodiment, in Fig. 1 Shown He described process can needed by manager or is being expected for the current of knowledge base Start in the case of data.Therefore, providing with described process shown in Fig. 1 represents volume Performance impact data and space save data.
Shown in Fig. 1 and described process can be referred to as background process.Assessment is to choosing The copy of the volume selected performs, and does not affect the performance about volume itself.An embodiment In, perform the application identical with Sampling techniques at the background process copy to compressing or simplify and perform While, continue to process data on the volume being uncompressed or do not simplified.Obtain and send out on backstage Raw space is saved and performance impact data, so that in the case of needs space-saving techniques, Housebroken decision-making may determine which volume and/or cluster can be with the quilts to performance impact minimum Compress or simplify.
With reference to Fig. 2, it is provided that illustrate the flow chart (200) of the process saved for estimation space. At any given time point, it is possible to use the measure of time (temporal being stored in knowledge base Measurement) estimate that the space from being compressed volume copy or simplify is saved.Deposit Storage data in the volume of data center are dynamic, continue because data are processed along with application The continuous object that is read or write rolls up (subject volume).As shown in Figure 1 and institute Describe, obtain the data (210) knowledge base from background process.Concurrently there are and data Real-time (live) capacity that volume in the minds of in is associated uses and acess control (220).Should Real time data relates to filling later being associated with storage volume of knowledge base from previously from background process Change.Such real time data includes but not limited to read deletes with the quantity of write request, data Quantity etc. except request.In one embodiment, after utilizing one or more enumerator to follow the tracks of Platform process execution between use data in real time.Receive step (210) from knowledge base with And in step (220) from the data of real-time statistics as estimation (projection) model Input (230).Utilize more specifically, these input data are estimated model to find out data center One or more volumes in have how many data to be changed after previous estimation.At one In embodiment, in step (230), linear regression model (LRM) is utilized to estimate to increase estimation.One In individual embodiment, use or many between measurement and the current time found in knowledge base The I/O access module that individual volume is experienced is predicted and is measured what later space was saved from last Change.After the estimation of step (230), priority (priority) mark is distributed to Data center stands each volume (240) of assessment.In one embodiment, can be based on phase Volume is ranked up by the priority score of association, and then these priority score can be used for Identify the one or more volumes for compressing or simplify efficiently.Therefore, herein shown in estimate Meter process utilize static and dynamic memory data come for potential space-saving techniques to one or Multiple row that involve in are classified.
It is important to assure that pond is less than their capacity.In one embodiment, threshold will be stored Value is set below the value of actual capacity to guarantee that this capacity is not exceeded.Such as, a reality Execute in example, space-saving techniques (such as compress or simplify) at the storage pool being associated with 80% Occur during volume operation.With reference to Fig. 3, it is provided that illustrate the place for predicting storage threshold-violating The flow chart (300) of reason.As directed, for violating the input of prediction with at least three kinds of forms Data (include but not limited to, it is contemplated that new storage allotment (310), storage pool capacity makes Use with threshold value (320) and capacity and increase (330)) enter.In one embodiment, Step (310) place expection allotment provided by manager, or it based on allotment history and by advance Survey.In one embodiment, the capacity at step (320) place is based on the storage volume being associated The fixed value of size, but in one embodiment, this value can be based on data transmission and/or pressure Contract or simplify and stand to change.In one embodiment, capacity uses growth (330) to relate to depositing The fluctuation of the scope that reservoir uses.Such as, if volume has been added or has been removed from pond.Connect Receive from (310), (320) and (330) data as be used for predict storage pool capacity The input (340) of the time violated.From the output (350) of prediction steps (340) with directly Produce to the time of threshold-violating and the form of storage pool.More specifically, step (340) place Violate the output data of the form of time Estimate that prediction provides capacity will to be exceeded at that time (350).In one embodiment, time Estimate can be based on each volume, based on gathering of rolling up Class or based on storage pool.Therefore, as shown in this article and described process be utilized Violate with prediction time threshold based on multiple factors (including the adaptation to the fluctuation in using).
The establishment of knowledge base, safeguard and in the target that utilizes one is prediction and guarantees storage Volume threshold value is not breached.With reference to Fig. 4, it is provided that illustrate the flow chart (400) of management memory capacity. Four elements are utilized as minimizing the performance reduction being associated with storage volume management (also Be referred to as optimize) input data.Input for optimizing includes: as shown in Figure 3 and The described time Estimate to capacity violation (410), as shown in Figure 2 and described (420), acceptable pond threshold value (430) and Admin Administration's plan are saved in the space estimated Slightly (440).Pond threshold value (430) can be quiescent value, or in one embodiment, is Dynamic value.In one embodiment, the strategy at step (440) place relates to about compression or simplifies Guidance because each during the space of these forms is saved is different, and may be in impact On there is difference.In one embodiment, the space saving at step (420) place can be according to profit Technology and different.Data from step (410)-(440) stand to optimize (450) Reduce for minimizing performance.Coming that the output of self-optimizing (460) includes can be to each storage Priorization (prioritize) list of all storage trace reduction actions that pond is taked.As herein Shown in, three storage pools (462), (464) and (466) are illustrated as based on for print The order of priority (prioritization) that mark reduces is ranked up.In one embodiment, often The volume of individual storage pool has action lists based on prioritization.Such as, sequence can be based on The result (product) that volume space is saved and I/O time delay increases.In one embodiment, row Sequence is to carry out by the order performing one or more actions, and the one or more action is from Substantial amounts of saving produces saving to the saving of minimum.In one embodiment, action lists Sequence is processed to volume selection and brings efficiency, and wherein, this list shows the order of priority made the test.Cause This, the storage pool in investigation is ranked up by the output carrying out self-optimizing.
As directed, the optimization at step (460) place carrys out filter action based on the feasibility completed, In one embodiment, this uses the model of the deadline reduced for the space estimated.Tool Body ground, can not occur if space reduces in the time required, then there may be space and violate. The estimation of deadline can affect the list of storage pool (462), (464) and (466) Sequence.In one embodiment, the quantity of the storage pool in list can change, and with regard to this In a bit, herein shown in and described quantity be only example, and should be by It is considered to limit.From step (460) place optimization export after, to each specify deposit Reservoir performs the storage reduction action of one or more volumes.More specifically, by variable NTotalDistribute to The quantity (470) of the ranked storage pool in output listing, and to the storage pool being associated Counting variable N carries out initializing (472).To storage poolNPerform storage reduction action (474).Then determine whether that reaching acceptable storage pool uses threshold value, so that when this Between point need not further action (476).The negative of the determination at step (476) place is rung Should be followed of and make storage pool counting variable be incremented by (478) and return to step (474). But, the positive response to the determination at step (476) place terminates storage pool reduction action (480). In one embodiment, the storage in pond of minimal time for arrive threshold-violating is first carried out Reduction action, the time then arriving at threshold-violating is time little, etc..Therefore, available storage sky Between trace managed in coherent mode, effectively and efficiently to make it possible to depositing The impact minimum of storage performance carries out the lasting storage of data.
Shown in Fig. 1-4 and described processing illustrates the estimation and knowledge making storage trace reduce Not and the actual rectification uncoupling of memory space.This uncoupling introduces method based on model Solve the dynamic characteristic of data storage.More specifically, subtracted by capacity in persistent storage medium Little optimization (such as simplify and compress) realizes capacity and saves.
With reference to Fig. 5, it is provided that illustrate the block diagram (500) of the assembly of storage pool capacity management system. As directed, process node (510) and be illustrated as communicating with data center (550).Process joint Point (510) has processor (512), this processor (512) also referred herein as place Reason unit, it strides across bus (514) and is operatively coupled to memorizer (516).Process joint Point (510) is further provided as communicating with other node (520), described other node (520) Each with safeguard in the data center (550) persistently store communication.Process node (510) The storage and maintenance of the data being responsible in data center (550).More specifically, node (510) Have and support storage pool capacity management based on capacity estimation and the uncoupling of capacity saving execution One or more instruments.As shown in this article and detailed hereafter, these body of tool Show and be made up of two modules (include uncoupling module (530) and select module (540)) Adaptable System.The function of uncoupling module (530) is to estimate from one or more skies Between reduce action capacity save.The function selecting module (540) is threshold value based on prediction Violate the subset being dynamically selected and performing space reduction action.
As directed, data center (550) be configured with multiple lasting storage volume (552), (554), (556), (558) and (560).Although only show and describing five Volume, but this quantity is not construed as limiting.In one embodiment, data center (550) Controller (570) including the management promoting storage volume.As directed, storage control (570) Being shown to have processor (572), this processor (572) is operable via bus (574) Be coupled to memorizer (576).Controller (570) leads to module (530) and (540) Letter.More specifically, management controls, to be delivered to controller via these modules any to promote Management action execution in storage volume.
The function of uncoupling module (530) is to make relevant to the reduction action of one or more spaces The estimation that the capacity of connection is saved separates with the actual execution of these actions.In separating treatment, go Coupling module (530) utilizes the method for sampling based on similarity, so that data center (550) In volume can be placed in group (also referred to as based on similarity cluster), be such as mapped to The volume of same application shows the similar random and reading of order and write I/O ratio etc.. Such as, as shown in this article, volume (552) and (554) is placed in first group of groupA(580) In, and roll up (556), (558) and (560) and be placed in second group of groupB(582) in. Although illustrate only two groups, but this quantity being example, and it is not construed as limiting. Meanwhile, the packet of volume is not static, but stands to change.From cluster one or more Other volume that the data analyzing acquisition of volume can be pushed out in cluster, but it is according to similar Property agreement.Therefore, the subset of the volume can being limited in any given cluster is analyzed.
As it is shown in figure 5, the one or more volumes in Ju Lei are selected for relevant to capacity management The analysis of connection.Uncoupling module (530) is responsible for capacity management, more specifically, be responsible for cluster In at least one select volume perform space reduction action and with and space reduce be associated The research that is associated of the impact on storage system and storage performance.More specifically, decoupling matched moulds Block is measured and is reduced the capacity saving being associated with space, is switched to subtract by the live load being associated The copy of little volume, from the live load measurement performance of switching, records any performance and reduces, and And then remove reduction so that system can be restored back to previous state.From uncoupling module (530) data that are that collect and that be associated make to manage, with memory capacity, the prediction being associated can Carried out reflectingly and performed.Prediction can be converted into and guarantee to be available for data storage The action of capacity.Similarity between various clusters based on volume, uncoupling module (530) Can be for the volume in cluster or cluster, the volume simplifying based on standing from this cluster or compress The measurement obtained infers that capacity is saved and performance reduces.
Memory capacity threshold value is to be managed so that there is enough storage skies that management data process Between key factor.In one embodiment, this threshold value and in storage volume the hundred of remaining space Proportion by subtraction is relevant.In any time that volume is compressed or simplifies, existence is all negatively affected by performance. Target is to be compressed one or more volumes when needed or simplify.In this regard, deposit In the balance way performed between uncoupling module (530) and selection module (540), its Middle uncoupling module (530) is at running background, and selects module (540) at front stage operation. Select module (540) based on prediction capacity threshold violate come from storage pool select for compression or The one or more volumes simplified.In one embodiment, uncoupling module (530) create and Safeguard the list (590) of the candidate volume reduced in each pond for space.This list (590) Save and performance measurement corresponding to capacity.In one embodiment, list (590) is arranged Sequence, and distribute priority with the volume in selective listing (590).Select module (540) Selection and the execution of storage volume occur when needed.In one embodiment, module (540) is selected Their selection is carried out based on ranked list (590).List (590) is illustrated as embedding Enter in memorizer (516), but in one embodiment, list (590) can be deposited Storage is in this locality of the data center (550) of controller (570) this locality.
Volume in storage pool can be static quantity.But in one embodiment, volume can be by Add or remove from storage pool.Communication with volume is uninterrupted.One or more process nodes with Storage pool communication is to support to need the reading to one or more storage volume and/or write operation Application processes.The communication process processed between node and storage pool is referred to as I/O.A reality Executing in example, I/O pattern can be visual processing between node and the storage volume being associated. Uncoupling module (530) can utilize I/O pattern to predict from the previous survey to the volume in cluster Measure the change that later space is saved and used.More specifically, uncoupling module (530) is permissible Update and measure, thus the measured data being associated with volume after creating estimation, wherein said Measured data are associated with renewal based on I/O pattern.In one embodiment, measurement Update the inefficacy including any previous measurement.Therefore, it can based on the actual access for volume Pattern updates to involving in row sampling and assessing the measurement data of memory capacity.
System described in Fig. 5 is by the instrument of the form by module (530) and (540) Mark.These instruments can be implemented in programmable hardware device, and described programmable hardware sets Standby such as field programmable gate array, programmable logic array, PLD etc..This A little instruments can also be implemented in the software performed for various types of processors.Generation can be performed The functional unit of the mark of code can such as include can being such as organized as object, process, merit One or more physically or logically blocks of the computer instruction of energy or other structure.While it is true, The executable file of these instruments is also without being physically located together, but can include depositing The storage instruction differed in diverse location, these instructions are when being joined logically together together Constitute the purposes stated of these instruments and implementation tool.
It practice, executable code can be the most multiple instruction of single instruction, and even may be used To be distributed on some different code segments, between different application and across some memorizeies Equipment.Similarly, operation data can be identified in pond in this article and illustrate, and can In being presented as any suitable form and being organized in the data structure of any suitable type. Operation data can be collected as individual data collection, or can be distributed on different positions (bag Include in different storage devices), and can be at least partly as in system or network Electronic signal exists.
Additionally, described feature, structure or characteristic can in one or more embodiments by Combine in any suitable manner.In the following description, it is provided that many concrete details are (all Example such as agency), to provide the thorough understanding of embodiment.But, the technology of association area Personnel are it will be recognized that these embodiments can one or more in not having these details In the case of be carried out, or can implement with other method, assembly, material etc..At it In the case of it, it is thus well known that structure, material or operation are not illustrated in more detail or describe, To avoid each side making embodiment to obscure.
Instrument shown in herein and described supports that the storage volume in the pond of multiple storage volume is held Management and the threshold-violating based on prediction of amount are adaptive selected reduced for space Individual or multiple volumes.As it has been described above, reduce, with space, branch (ramification) quilt being associated Perform as consistency operation, so that volume and the cluster being associated can be ranked (rank) And sequence, and the selection of the volume reduced for space is based on grade and sequence.An enforcement In example, classify and sort based on each frame, and in one embodiment, it is expanded To including that volume is organized in cluster therein classifies and sequence.Similarly, an enforcement In example, the function of capacity management and support and reduce for space to support the choosing of volume of management Select the cloud computing environment that can be pushed out to that there is shared resource pool.
Cloud computing environment is service-oriented, and feature concentrates on Stateless, lower coupling, mould Block and the interoperability of the meaning of one's words.The core of cloud computing is to comprise the foundation frame of interconnecting nodes network Structure.
With reference now to Fig. 6, which show an example of cloud computing node (610).Fig. 6 shows The cloud computing node (610) shown is only an example of the cloud computing node being suitable for, should be to this Function and the range of the embodiment of the present invention described by bring any restriction.In a word, cloud Calculate node (610) and can be utilized to implement and/or perform above-described any function.
Cloud computing node (610) has computer system/server (612), its can with numerous other Universal or special computing system environment or configuration operate together.It is known that be suitable to and computer The example of calculating system, environment and/or configuration that systems/servers (612) operates together include but Be not limited to: personal computer system, server computer system, thin client, thick client computer, Hand-held or laptop devices, system based on microprocessor, Set Top Box, programmable consumer electronics are produced Product, NetPC Network PC, minicomputer system large computer system and include above-mentioned The distributed cloud computing technology environment of meaning system, etc..
Computer system/server (612) can be in the computer system performed by computer system Describe under the general linguistic context of executable instruction (such as program module).Generally, program module can With include performing specific task or realize the routine of specific abstract data type, program, Target program, assembly, logic, data structure etc..Computer system/server (612) can be Performed in the distributed cloud computing environment of task real by the remote processing devices of communication network links Execute.In distributed cloud computing environment, program module may be located at this locality including storage device Or on remote computing system storage medium.
As shown in Figure 6, the computer system/server (612) in cloud computing node (610) is with logical With the form performance of the equipment of calculating.The assembly of computer system/server (612) can include but not It is limited to: one or more processor or processing unit (616), system storage (628), even Connect the bus (618) of different system assembly (including system storage (628) and processing unit (616)).
Bus (618) if represent in the bus structures of dry type one of any one type or Multiple, including memory bus or Memory Controller, peripheral bus, Accelerated Graphics Port, And use processor or the local bus of any one of various bus architecture.For example, And unrestricted, such framework includes Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MCA) bus, enhancing ISA (EISA) bus, VESA (VESA) Local bus and periphery component interconnection (PCI) bus.Computer system/server (612) Generally include various computer system-readable medium.Such medium can be can be by department of computer science Any usable medium that system/server (612) accesses, and it includes volatibility and non-volatile Property medium and removable and irremovable medium.
System storage (628) can include the computer system-readable of form of volatile memory Medium, such as random access memory (RAM) (630) and/or cache memory (632). It is removable/nonremovable, easily that computer system/server (612) may further include other The property lost/nonvolatile computer system storage medium.Being only used as citing, storage system (634) is permissible For reading and writing immovable, non-volatile magnetic media, (Fig. 6 does not shows, commonly referred to " hard Disk drive ").Although not shown in Fig. 6, it is provided that for removable non-volatile The disc driver that disk (such as " floppy disk ") is read and write, and to removable non-volatile light The CD drive that dish (such as CD-ROM, DVD-ROM or other light medium) is read and write. In these cases, each driver can be by one or more data media interfaces with total Line (618) is connected.Memorizer (628) can include at least one program product, and this program product has Having one group of (for example, at least one) program module, these program modules are configured to perform this The function of bright each embodiment.
There is the program/utility (640) of one group of (at least one) program module (642), can To be stored in memorizer (628), such program module (642) includes but not limited to operation system System, one or more application program, other program module and routine data, these examples In each or certain combination in potentially include the realization of network environment.Program module (642) is led to Often perform the function in embodiment described in the invention and/or method.
Computer system/server (612) can also be with one or more external equipments (614) (example Such as keyboard, sensing equipment, display (624) etc.) communication, also can make with one or more User can be mutual with this computer system/server (612) equipment communication, and/or with make this Computer system/server (612) can be with appointing that other calculating equipment one or more communicate What equipment (such as network interface card, modem etc.) communication.This communication can by input/ Output (I/O) interface (622) is carried out.Further, computer system/server (612) can also be led to Cross network adapter (620) and one or more network (such as LAN (LAN), wide area Net (WAN) and/or public network, such as the Internet) communication.As it can be seen, network is fitted Orchestration (620) is communicated with other module of computer system/server (612) by bus (618). It should be understood that although not shown in, other hardware and/or software module can be with departments of computer science System/server (612) operates together, includes but not limited to: microcode, device driver, redundancy Processing unit, external disk drive array, RAID system, tape drive and data standby Part storage system etc..
With reference now to Fig. 7, which show exemplary cloud computing environment (750).As it can be seen, Cloud computing environment (750) includes that the local computing device that cloud computing consumer uses can be with its phase One or more cloud computing node (710) of communication, local computing device can be such as individual Digital assistants (PDA) or mobile phone (754A), desktop computer (754B), notebook computer (754C) and/or Automotive Computer System (754N).Can phase intercommunication between cloud computing node (710) Letter.Privately owned cloud as above, community Cloud, public cloud or mixed can included but not limited to Close in one or more network of cloud or combinations thereof and cloud computing node (710) is carried out Physics or virtual group (not shown).So, the consumer of cloud is without at local computing Safeguard on equipment that the architecture that resource just can request that cloud computing environment (750) provides i.e. services (IaaS), platform i.e. services (PaaS) and/or software i.e. services (SaaS).Should be appreciated that All kinds of calculating equipment 54A-N that Fig. 7 shows are only schematically, cloud computing node (710) And cloud computing environment (750) can with in any type of network and/or network addressable is connected Any type of calculating equipment (such as using web browser) communicates.
With reference now to Fig. 8, which show one group of function modeling that cloud computing environment (800) provides Layer.It is understood in advance that, the assembly shown in Fig. 8, layer and function are only all schematically, Embodiments of the invention are not limited to this.As shown in Figure 8, it is provided that following layers and corresponding function:
Hardware and software layer (810), virtualization layer (820), management level (830) and work Make load layer (840).Hardware and software layer (810) includes nextport hardware component NextPort and component software. The example of nextport hardware component NextPort includes: large scale computer, in one example,System； Server based on RISC (reduction instruction set computer) framework, in one example, IBMSystem；IBMSystem；IBMSystem；Storage sets Standby；Network and networking components.The example of component software includes: network application server software, In one example, IBMApplication server software；And database software, In one example, IBMDatabase software.(IBM、zSeries、pSeries、 XSeries, BladeCenter, WebSphere and DB2 are International Business The trade mark that Machines Corporation registers in whole world many compasss of competency).
Virtual level (820) provides a level of abstraction, and this layer can provide the example of following pseudo-entity Son: virtual server, virtual memory, virtual network (including virtual private networks), virtual Application and operating system, and virtual client.
In one example, management level (830) can provide following functions: resource is pre-configured, Metering and price, portal user, Service level management and key management.These are described below Function.The pre-configured offer of resource is utilized to perform the calculating resource of task in cloud computing environment Dynamic acquisition with other resource.Metering and price provide the resource utilized in cloud computing environment Cost tracing and for the bill of consumption of these resources and invoice.In one example, These resources can include that application software is permitted.Safety provides identity for cloud consumer and task Certification, and provide protection for data and other resource.Portal user is consumer and system pipes Reason person provides the access to cloud computing environment.
Live load layer (840) provides and it can be utilized the example of function of cloud computing environment. The shared pool (hereinafter referred to as cloud computing environment) of configurable computer resource described herein In, file can be in the use in multiple data centers (also referred herein as data station) Share between family.Therefore, provide a series of mechanism in supporting cloud computing environment in shared pool Data storage organization and management.
Shown in herein and described process discusses its function and is to manage storage pool capacity Assembly.Specifically, exist by practically at least one volume in each pond being compressed Or simplify and obtain the data being associated with the affairs on the volume compressed or simplify and obtain accurately The background process estimated.Then utilize the data of acquisition to estimate other volume in same pond Behavior.Foreground processes and utilizes back-end data to save execution to solve capacity.Background process and foreground Process makes estimation correct uncoupling with actual.
The present invention with detailed description can be system, method and/or calculating as shown in the drawings Machine program product.This computer program can include computer-readable recording medium ( Or multiple), it has for making processor perform the computer-readable of each aspect of the present invention Programmed instruction.
Computer-readable recording medium can be can to keep and store for instruction execution equipment The tangible device of instruction.Computer-readable recording medium can be such as, but not limited to, electricity Sub-storage device, magnetic storage apparatus, optical storage apparatus, electromagnetism storage device, quasiconductor are deposited Storage equipment or any suitable combination of aforementioned storage device.Computer-readable recording medium The non-exhaustive listing of more object lessons includes following: portable computer diskette, hard disk, with Machine access memorizer (RAM), read only memory (ROM), erasable programmable are read-only Memorizer (EPROM or flash memory), static RAM (SRAM), portable Formula compact disk read only memory (CD-ROM), digital versatile disc (DVD), memory stick, Floppy disk, mechanical coding equipment (such as record the punched card in the groove having instruction or raise on it Structure) and any suitable combination of aforementioned storage medium.Calculate as used in this article Machine readable storage medium storing program for executing itself is not construed as temporary transient signal, such as radio wave or other freedom The electromagnetic wave propagated, the electromagnetic wave propagated by waveguide or other transmission medium (such as, are passed through The light pulse of fiber optic cables) or by the signal of telecommunication of wire transmission.
Computer-readable program instructions described herein can be from computer-readable recording medium It is downloaded to each calculating/processing equipment, or via network (such as, the Internet, LAN, wide Territory net and/or wireless network) download to outer computer or External memory equipment.Network can include Copper transmission cable, Transmission Fibers, be wirelessly transferred, router, fire wall, switch, gateway Computer and/or Edge Server.Network adapter cards in each calculating/processing equipment or network Interface receives computer-readable program instructions from network, and forwards these computer-readable programs Instruction is in the computer-readable recording medium being stored in each calculating/processing equipment.
Can be that assembly program refers to for performing the computer-readable program instructions of the operation of the present invention Make, instruction set architecture (ISA) instruction, machine instruction, machine-dependent instructions, microcode, Firmware instructions, condition setup data or any combination with one or more programming languages are write Source code or object code, described programming language includes OO programming language (such as Smalltalk, C++ etc.) and traditional procedural (such as " C " programming language Or similar programming language).Computer-readable program instructions can be completely at the computer of user Upper execution, partly on the computer of user, performs as stand alone software bag, partly exists On the computer of user and perform the most on the remote computer, or completely in remote computation Perform on machine or server.In the case of the latter, remote computer can be by any type Network be connected to (including LAN (LAN) or wide area network (WAN)) calculating of user Machine, or connection (such as, the use Internet service offer of outer computer is provided Business passes through the Internet).In certain embodiments, electronic circuit (includes such as FPGA Circuit, field programmable gate array (FPGA) or programmable logic array (PLA)) Electronic circuit personalization can be made to hold by the status information utilizing computer-readable program instructions Row computer-readable program instructions, in order to perform each aspect of the present invention.
Each aspect of the present invention is herein with reference to method according to an embodiment of the invention, device (system) and the flow chart of computer program and/or block diagram are described.It will be appreciated that stream The combination of the frame in each frame in journey figure and/or block diagram and flow chart and/or block diagram can be by Computer-readable program instructions realizes.
These computer-readable program instructions can be provided to general purpose computer, special-purpose computer Or the processor of other programmable data processing means is to generate machine so that via computer or The instruction that the processor of other programmable data processing means performs create for flowchart and / block diagram in a frame or multiple frame in the means of function/action specified.These computers can Reader instruction can also be stored in can guide computer, programmable data processing means and/ Or in the computer-readable recording medium that operates in a specific way of miscellaneous equipment, so that wherein depositing The computer-readable recording medium containing instruction includes manufacture, and this manufacture includes realizing flow process The instruction of each side of function/action specified in a frame in figure and/or block diagram or multiple frame.
Computer-readable program instructions can also be loaded at computer, other programmable data On reason device or miscellaneous equipment so that sequence of operations step at this computer, other is able to programme Be performed to generate computer on device or miscellaneous equipment and realize process so that this computer, In the instruction flowchart performed on other programmable device or miscellaneous equipment and/or block diagram Function/the action specified in one frame or multiple frame.
Flow chart and block diagram in accompanying drawing illustrate system according to various embodiments of the present invention, side Method and framework in the cards, function and the operation of computer program.In this, Each frame in flow chart or block diagram can be with representation module, program segment or operation part, and it includes For realizing one or more executable instructions of the logic function specified.Substitute at some and realize In, in frame, the function of mark can not press the order appearance of mark in accompanying drawing.Such as, show continuously Two frames gone out in fact can be performed substantially simultaneously, or these frames sometimes can be by Reversed sequence performs, and this depends on the function related to.It will also be noted that, in block diagram and/or flow chart Each frame and block diagram and/or flow chart in the combination of frame can be by special based on hardware System realize, these systems perform the function specified or action, or perform specialized hardware and The combination of computer instruction.
Term used herein is merely for the sake of the purpose of description specific embodiment, and not anticipates Figure limits the present invention.As used herein, singulative " " and " being somebody's turn to do " are intended to also Including plural form, indicate unless the context clearly.It will be appreciated that term " bag Include " and/or specify time " comprising " is used in this manual stated feature, integer, The existence of step, operation, element and/or assembly, but be not excluded for one or more further feature, The existence of integer, step, operation, element, assembly and/or combinations thereof or interpolation.
All means in following claims or step add the counter structure of functional element, material, Action and equivalent are intended to include for claimed with other as specifically claimed Element combinations performs any structure, material or the action of function.Description of the invention is in order at example The purpose shown and describe presents, but is not intended to invention that is exhaustive or that be limited to disclosed form. Without departing from the scope and spirit of the present invention, many amendments and modification are for this area Technical staff will be apparent from.Embodiment is chosen and description is to explain the present invention best Principle and actual application, and make the others of ordinary skill in the art can be for tool There are the various embodiments of the various amendments of specific use being suitable for being considered to understand the present invention. Therefore, the realization of background process makes storage volume can continue to support application, capacity management simultaneously Function be to ensure that the availability of enough memory spaces.
Although it will be appreciated that describing the concrete of the present invention the most for illustrative purposes Embodiment, but without departing from the spirit and scope of the present invention, can carry out various Amendment.Therefore, protection scope of the present invention is only limited by appended claims and equivalent thereof.

Claims (12)

1. for managing a computer implemented method for the capacity of storage pool, including:
Make estimation and the one saved from the capacity of one or more spaces reduction action or The actual execution uncoupling of multiple spaces reduction action, described uncoupling includes:
Select the subset of volume from each pond, and the copy of the subset of each selection is performed First space reduction action, described volume operates with the first state；
The capacity that the subset measured and select is associated changes, and capacity is changed data Record is in primary importance；
Measure the performance change from the live load in the subset selected, and by performance Change data record in the second position；And
Generating the subset for the optimal spatial reduction action performed, described action is based on record Capacity and performance change data；With
When needed perform come self-generating optimal spatial reduction action subset at least one move Making, described execution makes described first State Transferring be the second state.
Method the most according to claim 1, also includes: safeguard in each pond for space The list of the candidate volume reduced, described list is saved with corresponding capacity and performance measurement is associated.
Method the most according to claim 2, also includes: for each storage pool, to institute State and list involves in row major.
Method the most according to claim 1, also includes: for not selected in described pond Volume infer that capacity is saved and performance reduces, wherein, described deduction is based on from the volume selected Measure.
Method the most according to claim 1, also includes: prediction is after previous measurement The change saved of space, described prediction utilizes the I/O access module observed for each volume.
Method the most according to claim 5, also includes: be updated periodically described measurement, Lost efficacy including making any previous measurement data.
7. a computer system, including:
Processing unit, described processing unit is operatively coupled to memorizer；
Storage pool, described storage pool has two or more storage volume, is operatively coupled to Described processing unit；
With described processing unit communication to manage the instrument of the capacity of described storage pool, described instrument Including:
Uncoupling module, described uncoupling module is for estimating from one or more spaces The capacity of reduction action is saved and actual the holding of the one or more space reduction action OK, described uncoupling module is used for:
The subset of volume, and the copy of the subset to each selection is selected from each pond Performing the first space reduction action, described volume operates with the first state；
The capacity that the subset measured and select is associated changes, and is changed by capacity Data record is in primary importance；
Measure the performance change from the live load in the subset selected, and will Performance change data record is in the second position；
Selecting module, described selection module reduces dynamic for generating the optimal spatial for performing The subset made, described action capacity based on record and performance change data；And
Described selection module is for the optimal spatial reduction action that performs when needed to generate At least one action in subset, described execution makes described first State Transferring be the second shape State.
System the most according to claim 7, also includes: described uncoupling module is used for tieing up Protecting the list of the candidate volume reduced in each pond for space, described list is saved and property with capacity Can measure and be associated.
System the most according to claim 8, also includes: for each storage pool, described Uncoupling module is for each volume distribution priority in described list.
System the most according to claim 7, also includes: described uncoupling module is used for For in described pond, non-selected volume deduction capacity is saved and performance reduces, wherein, push away described in Disconnected based on the measurement from the volume selected.
11. systems according to claim 7, also include: described uncoupling module is used for Predicting and measure, from previous, the change that later space is saved, described prediction utilizes for each volume The I/O access module observed.
12. systems according to claim 11, also include: the renewal of described measurement, bag Include the inefficacy of any previous measurement data.
CN201610164308.9A 2015-03-31 2016-03-22 Storage pool capacity management Active CN106020715B (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US14/675,151 2015-03-31
US14/675,151 US10248319B2 (en) 2015-03-31 2015-03-31 Storage pool capacity management

Publications (2)

Publication Number Publication Date
CN106020715A true CN106020715A (en) 2016-10-12
CN106020715B CN106020715B (en) 2019-03-19

Family

ID=57016167

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610164308.9A Active CN106020715B (en) 2015-03-31 2016-03-22 Storage pool capacity management

Country Status (2)

Country Link
US (2) US10248319B2 (en)
CN (1) CN106020715B (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107577431A (en) * 2017-09-07 2018-01-12 郑州云海信息技术有限公司 A kind of storage pool construction method and device
CN110413198A (en) * 2018-04-28 2019-11-05 伊姆西Ip控股有限责任公司 For managing the method, equipment and computer program product of storage system
CN113419672A (en) * 2021-06-04 2021-09-21 济南浪潮数据技术有限公司 Storage capacity management method, system and storage medium
CN114341794A (en) * 2019-09-06 2022-04-12 国际商业机器公司 Converting large extent storage pools to small extent storage pools as appropriate

Families Citing this family (23)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170109055A1 (en) * 2015-10-15 2017-04-20 Pure Storage, Inc. Capacity planning in a multi-array storage system
US10074066B2 (en) 2016-01-16 2018-09-11 International Business Machines Corporation Two phase predictive approach for supply network optimization
US11502972B2 (en) * 2016-08-28 2022-11-15 Vmware, Inc. Capacity optimization in an automated resource-exchange system
KR20180127695A (en) * 2017-05-22 2018-11-30 삼성전자주식회사 Apparatus for securing storage space and method thereof
US11086533B2 (en) * 2018-08-31 2021-08-10 Wipro Limited Method and system for optimizing storage space in a storage unit
US10754720B2 (en) 2018-09-26 2020-08-25 International Business Machines Corporation Health check diagnostics of resources by instantiating workloads in disaggregated data centers
US11188408B2 (en) 2018-09-26 2021-11-30 International Business Machines Corporation Preemptive resource replacement according to failure pattern analysis in disaggregated data centers
US10831580B2 (en) * 2018-09-26 2020-11-10 International Business Machines Corporation Diagnostic health checking and replacement of resources in disaggregated data centers
US10838803B2 (en) 2018-09-26 2020-11-17 International Business Machines Corporation Resource provisioning and replacement according to a resource failure analysis in disaggregated data centers
US10761915B2 (en) 2018-09-26 2020-09-01 International Business Machines Corporation Preemptive deep diagnostics and health checking of resources in disaggregated data centers
US11050637B2 (en) 2018-09-26 2021-06-29 International Business Machines Corporation Resource lifecycle optimization in disaggregated data centers
US10855757B2 (en) * 2018-12-19 2020-12-01 At&T Intellectual Property I, L.P. High availability and high utilization cloud data center architecture for supporting telecommunications services
CN111813322B (en) * 2019-04-11 2023-06-13 杭州海康威视***技术有限公司 Storage pool creation method, device, equipment and storage medium
US11481117B2 (en) * 2019-06-17 2022-10-25 Hewlett Packard Enterprise Development Lp Storage volume clustering based on workload fingerprints
US10936464B2 (en) * 2019-07-29 2021-03-02 EMC IP Holding Company LLC Method and system for countering capacity shortages on storage systems
CN112578992B (en) * 2019-09-27 2022-07-22 西安华为技术有限公司 Data storage method and data storage device
US11106365B1 (en) 2020-02-10 2021-08-31 EMC IP Holding Company LLC Flow control of input/output (IO) in a synchronous replication session
US11061835B1 (en) * 2020-02-12 2021-07-13 EMC IP Holding Company LLC Sensitivity matrix for system load indication and overload prevention
CN111966288B (en) * 2020-08-07 2022-08-09 苏州浪潮智能科技有限公司 Method, system, device and medium for cleaning storage pool
US11561722B2 (en) 2020-08-25 2023-01-24 Micron Technology, Inc. Multi-page parity data storage in a memory device
US11675536B2 (en) * 2020-10-13 2023-06-13 EMC IP Holding Company LLC Intelligent scheduling for garbage collection
US11586422B2 (en) * 2021-05-06 2023-02-21 International Business Machines Corporation Automated system capacity optimization
JP7429214B2 (en) * 2021-10-07 2024-02-07 株式会社日立製作所 Storage system and data replication method in storage system

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100281079A1 (en) * 2009-04-30 2010-11-04 Oracle International Corporation Compression analyzer
US20140143517A1 (en) * 2012-11-19 2014-05-22 Hitachi, Ltd. Storage system
CN103842972A (en) * 2011-09-28 2014-06-04 国际商业机器公司 Automated selection of functions to reduce storage capacity based on performance requirements

Family Cites Families (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7702873B2 (en) 2005-04-25 2010-04-20 Network Appliance, Inc. Managing common storage by allowing delayed allocation of storage after reclaiming reclaimable space in a logical volume
US7933936B2 (en) 2005-06-10 2011-04-26 Network Appliance, Inc. Method and system for automatic management of storage space
JP4806556B2 (en) 2005-10-04 2011-11-02 株式会社日立製作所 Storage system and configuration change method
US8244868B2 (en) 2008-03-24 2012-08-14 International Business Machines Corporation Thin-provisioning adviser for storage devices
US8341119B1 (en) * 2009-09-14 2012-12-25 Netapp, Inc. Flexible copies having different sub-types
US8407445B1 (en) 2010-03-31 2013-03-26 Emc Corporation Systems, methods, and computer readable media for triggering and coordinating pool storage reclamation
US20110307492A1 (en) * 2010-06-15 2011-12-15 Rovi Technologies Corporation Multi-region cluster representation of tables of contents for a volume
US8438362B2 (en) 2010-06-15 2013-05-07 Symantec Corporation Automatically reclaiming memory space
US8751768B2 (en) 2011-04-29 2014-06-10 Symantec Corporation Data storage reclamation systems and methods
US9158706B2 (en) 2011-10-31 2015-10-13 International Business Machines Corporation Selective space reclamation of data storage memory employing heat and relocation metrics
US9038068B2 (en) 2012-11-15 2015-05-19 Bank Of America Corporation Capacity reclamation and resource adjustment
US9003135B2 (en) 2013-01-15 2015-04-07 International Business Machines Corporation Efficient allocation and reclamation of thin-provisioned storage
US9524201B2 (en) * 2014-06-19 2016-12-20 Avago Technologies General Ip (Singapore) Pte. Ltd. Safe and efficient dirty data flush for dynamic logical capacity based cache in storage systems

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100281079A1 (en) * 2009-04-30 2010-11-04 Oracle International Corporation Compression analyzer
CN103842972A (en) * 2011-09-28 2014-06-04 国际商业机器公司 Automated selection of functions to reduce storage capacity based on performance requirements
US20140143517A1 (en) * 2012-11-19 2014-05-22 Hitachi, Ltd. Storage system

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107577431A (en) * 2017-09-07 2018-01-12 郑州云海信息技术有限公司 A kind of storage pool construction method and device
CN110413198A (en) * 2018-04-28 2019-11-05 伊姆西Ip控股有限责任公司 For managing the method, equipment and computer program product of storage system
CN110413198B (en) * 2018-04-28 2023-04-14 伊姆西Ip控股有限责任公司 Method, apparatus and computer program product for managing a storage system
CN114341794A (en) * 2019-09-06 2022-04-12 国际商业机器公司 Converting large extent storage pools to small extent storage pools as appropriate
CN113419672A (en) * 2021-06-04 2021-09-21 济南浪潮数据技术有限公司 Storage capacity management method, system and storage medium
CN113419672B (en) * 2021-06-04 2023-06-13 济南浪潮数据技术有限公司 Storage capacity management method, system and storage medium

Also Published As

Publication number Publication date
US20190107955A1 (en) 2019-04-11
US10248319B2 (en) 2019-04-02
US10620839B2 (en) 2020-04-14
CN106020715B (en) 2019-03-19
US20160291876A1 (en) 2016-10-06

Similar Documents

Publication Publication Date Title
CN106020715A (en) Storage pool capacity management
CN106020940B (en) For determining the method and system of the storage tier of the placement of data set
CN103377091B (en) The method and system efficiently performed of the operation in resource-sharing pond
CN105808634A (en) Distributed map reduce network
CN104731574B (en) For identifying the method and system of the resource bottleneck in multistage operating stream process
US20190188742A1 (en) Forecasting demand across groups of skills
US20170124492A1 (en) System for automated capture and analysis of business information for reliable business venture outcome prediction
US20200034776A1 (en) Managing skills as clusters using machine learning and domain knowledge expert
US20240214428A1 (en) Platform for management and tracking of collaborative projects
US20180247234A1 (en) Platform for management and tracking of collaborative projects
CN107430528A (en) Opportunistic resource migration is placed with optimizing resource
CN104796270A (en) Method and device for recommending suspicious components during problem diagnosis of cloud application
US11593735B2 (en) Automated and efficient personal transportation vehicle sharing
CN103814358A (en) Virtual machine placement within server farm
CN104424013A (en) Method and device for deploying virtual machine in computing environment
CN103365725A (en) Method and system for dynamic allocation of workload deployment units across a plurality of clouds
CN110389824A (en) Handle method, equipment and the computer program product of calculating task
Yang A novel cloud information agent system with Web service techniques: Example of an energy-saving multi-agent system
CN103299274A (en) Determining an optimal computing environment for running an image
CN106534291A (en) Voltage monitoring method based on big data processing
CN103581339A (en) Storage resource allocation monitoring and processing method based on cloud computing
Feng et al. [Retracted] Design and Simulation of Human Resource Allocation Model Based on Double‐Cycle Neural Network
CN106066812A (en) Historical information management resource based on application
JP2006048702A (en) Automatic configuration of transaction-based performance model
CN103595815A (en) Method for distributing storage resources based on cloud computing

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant